import numpy as np
import pandas as pd 

Data Reading

df=pd.read_csv(r"C:\Users\HOME\Downloads\archive (1)\PS_20174392719_1491204439457_log.csv")

df

	step	type	amount	nameOrig	oldbalanceOrg	newbalanceOrig	nameDest	oldbalanceDest	newbalanceDest	isFraud	isFlaggedFraud
0	1	PAYMENT	9839.64	C1231006815	170136.00	160296.36	M1979787155	0.00	0.00	0	0
1	1	PAYMENT	1864.28	C1666544295	21249.00	19384.72	M2044282225	0.00	0.00	0	0
2	1	TRANSFER	181.00	C1305486145	181.00	0.00	C553264065	0.00	0.00	1	0
3	1	CASH_OUT	181.00	C840083671	181.00	0.00	C38997010	21182.00	0.00	1	0
4	1	PAYMENT	11668.14	C2048537720	41554.00	29885.86	M1230701703	0.00	0.00	0	0
...	...	...	...	...	...	...	...	...	...	...	...
6362615	743	CASH_OUT	339682.13	C786484425	339682.13	0.00	C776919290	0.00	339682.13	1	0
6362616	743	TRANSFER	6311409.28	C1529008245	6311409.28	0.00	C1881841831	0.00	0.00	1	0
6362617	743	CASH_OUT	6311409.28	C1162922333	6311409.28	0.00	C1365125890	68488.84	6379898.11	1	0
6362618	743	TRANSFER	850002.52	C1685995037	850002.52	0.00	C2080388513	0.00	0.00	1	0
6362619	743	CASH_OUT	850002.52	C1280323807	850002.52	0.00	C873221189	6510099.11	7360101.63	1	0

6362620 rows × 11 columns

data=df.copy()

Analysis

print(data.isnull().sum())

step              0
type              0
amount            0
nameOrig          0
oldbalanceOrg     0
newbalanceOrig    0
nameDest          0
oldbalanceDest    0
newbalanceDest    0
isFraud           0
isFlaggedFraud    0
dtype: int64

# Exploring transaction type
print(data.type.value_counts())

CASH_OUT    2237500
PAYMENT     2151495
CASH_IN     1399284
TRANSFER     532909
DEBIT         41432
Name: type, dtype: int64

Vizualization

type = data["type"].value_counts()
transactions = type.index
quantity = type.values

import plotly.express as px
figure = px.pie(data, 
             values=quantity, 
             names=transactions,hole = 0.5, 
             title="Distribution of Transaction Type")
figure.show()

Feature Selection

# Checking correlation
correlation = data.corr()
print(correlation["isFraud"].sort_values(ascending=False))

C:\Users\HOME\AppData\Local\Temp\ipykernel_1940\3404805963.py:2: FutureWarning:

The default value of numeric_only in DataFrame.corr is deprecated. In a future version, it will default to False. Select only valid columns or specify the value of numeric_only to silence this warning.

isFraud           1.000000
amount            0.076688
isFlaggedFraud    0.044109
step              0.031578
oldbalanceOrg     0.010154
newbalanceDest    0.000535
oldbalanceDest   -0.005885
newbalanceOrig   -0.008148
Name: isFraud, dtype: float64

data["type"] = data["type"].map({"CASH_OUT": 1, "PAYMENT": 2, 
                                 "CASH_IN": 3, "TRANSFER": 4,
                                 "DEBIT": 5})
data["isFraud"] = data["isFraud"].map({0: "No Fraud", 1: "Fraud"})
print(data.head())

   step  type    amount     nameOrig  oldbalanceOrg  newbalanceOrig  \
0     1     2   9839.64  C1231006815       170136.0       160296.36   
1     1     2   1864.28  C1666544295        21249.0        19384.72   
2     1     4    181.00  C1305486145          181.0            0.00   
3     1     1    181.00   C840083671          181.0            0.00   
4     1     2  11668.14  C2048537720        41554.0        29885.86   

      nameDest  oldbalanceDest  newbalanceDest   isFraud  isFlaggedFraud  
0  M1979787155             0.0             0.0  No Fraud               0  
1  M2044282225             0.0             0.0  No Fraud               0  
2   C553264065             0.0             0.0     Fraud               0  
3    C38997010         21182.0             0.0     Fraud               0  
4  M1230701703             0.0             0.0  No Fraud               0  

# splitting the data
from sklearn.model_selection import train_test_split
x = np.array(data[["type", "amount", "oldbalanceOrg", "newbalanceOrig"]])
y = np.array(data[["isFraud"]])

Data Splitting

# training a machine learning model
from sklearn.tree import DecisionTreeClassifier
xtrain, xtest, ytrain, ytest = train_test_split(x, y, test_size=0.10, random_state=42)

Model Training

model = DecisionTreeClassifier()
model.fit(xtrain, ytrain)

Prediction/Testing

print(model.score(xtest, ytest))

0.999732814469511

# prediction
#features = [type, amount, oldbalanceOrg, newbalanceOrig]
features = np.array([[4, 9000.60, 9000.60, 0.0]])
print(model.predict(features))

['Fraud']